OVERALL ACC: (BEFORE OUTPUT FORMATTER) 157 / 247 = 0.6356275303643725 -------------------------------------------------------------------------------- OVERALL ACC: (AFTER OUTPUT FORMATTER) 159 / 247 = 0.6437246963562753 Formatter Errors: ['D241Q07'] -------------------------------------------------------------------------------- AGGREGATOR PERFORMANCE: EASY: 157 / 158 = 0.9936708860759493 HARD: 0 / 34 = 0.0 -------------------------------------------------------------------------------- DISPATCHER AMODE TOP-3 PERFORMANCE: (COVERAGE) 243 / 247 = 0.9838056680161943 -------------------------------------------------------------------------------- DISPATCHER ATYPE-3 PERFORMANCE: (COVERAGE) 241 / 247 = 0.9757085020242915 -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN CORRECTLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 78 / 124 = 0.6290 Single-Span-Multi-Hop-Extraction 88 / 124 = 0.7097 Multi-Spans-Extraction 0 / 21 = 0.0000 YesNo 19 / 28 = 0.6786 Arithmetic-Operations 14 / 23 = 0.6087 Counting 0 / 0 = NaN Date-Duration 16 / 23 = 0.6957 Kinship 18 / 23 = 0.7826 Wiki-Json-Inference 0 / 0 = NaN Summarize 0 / 5 = 0.0000 -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN WRONGLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 31 / 123 = 0.2520 Single-Span-Multi-Hop-Extraction 33 / 123 = 0.2683 Multi-Spans-Extraction 12 / 226 = 0.0531 YesNo 0 / 219 = 0.0000 Arithmetic-Operations 3 / 224 = 0.0134 Counting 0 / 0 = NaN Date-Duration 4 / 224 = 0.0179 Kinship 3 / 224 = 0.0134 Wiki-Json-Inference 0 / 0 = NaN Summarize 0 / 242 = 0.0000 -------------------------------------------------------------------------------- ANSWER MODULE ERRORS (WHEN CORRECTLY ACTIVATED): Single-Span-Extraction: ['D001Q02', 'D007Q02', 'D007Q03', 'D013Q01', 'D013Q11', 'D031Q01', 'D031Q02', 'D037Q11', 'D037Q12', 'D049Q01', 'D049Q05', 'D049Q07', 'D073Q01', 'D073Q11', 'D079Q05', 'D079Q06', 'D079Q07', 'D085Q03', 'D085Q04', 'D085Q05', 'D085Q06', 'D091Q03', 'D115Q03', 'D115Q04', 'D115Q07', 'D127Q01', 'D181Q02', 'D181Q04', 'D181Q05', 'D181Q06', 'D247Q02', 'D247Q06', 'D253Q01', 'D253Q11', 'D253Q12', 'D271Q06', 'D283Q07', 'D289Q08', 'D289Q10', 'D289Q11', 'D295Q02', 'D295Q04', 'D295Q09', 'D301Q05', 'D307Q06', 'D325Q03'] Single-Span-Multi-Hop-Extraction: ['D007Q02', 'D007Q03', 'D013Q01', 'D013Q08', 'D013Q12', 'D031Q01', 'D031Q02', 'D037Q12', 'D049Q01', 'D049Q05', 'D061Q03', 'D073Q11', 'D079Q06', 'D079Q07', 'D085Q04', 'D091Q03', 'D097Q03', 'D115Q03', 'D115Q04', 'D115Q07', 'D127Q01', 'D181Q02', 'D211Q03', 'D211Q05', 'D247Q02', 'D247Q06', 'D253Q01', 'D253Q06', 'D289Q08', 'D295Q04', 'D295Q07', 'D301Q02', 'D307Q03', 'D307Q06', 'D325Q03', 'D325Q04'] Multi-Spans-Extraction: ['D001Q08', 'D007Q01', 'D007Q04', 'D007Q05', 'D013Q02', 'D031Q03', 'D031Q04', 'D049Q02', 'D073Q02', 'D073Q06', 'D073Q07', 'D073Q08', 'D073Q09', 'D085Q07', 'D115Q06', 'D115Q08', 'D127Q07', 'D241Q08', 'D241Q09', 'D313Q01', 'D313Q02'] YesNo: ['D037Q17', 'D037Q18', 'D115Q02', 'D127Q06', 'D253Q07', 'D301Q06', 'D313Q04', 'D313Q05', 'D325Q05'] Arithmetic-Operations: ['D049Q03', 'D073Q04', 'D085Q01', 'D085Q08', 'D247Q01', 'D247Q05', 'D247Q07', 'D247Q09', 'D283Q01'] Counting: [] Date-Duration: ['D061Q04', 'D073Q05', 'D097Q06', 'D103Q04', 'D241Q04', 'D247Q08', 'D259Q05'] Kinship: ['D037Q04', 'D037Q05', 'D037Q06', 'D091Q11', 'D091Q12'] Wiki-Json-Inference: [] Summarize: ['D001Q11', 'D049Q04', 'D073Q12', 'D103Q07', 'D289Q07'] --------------------------------------------------------------------------------